Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    欢

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     직
    -0.07
    печ
    -0.06
    sciously
    -0.06
    умент
    -0.06
    693
    -0.06
     акку
    -0.06
     контак
    -0.06
     wrongly
    -0.06
     Heck
    -0.06
    ентами
    -0.06
    POSITIVE LOGITS
    ourmet
    0.09
    欢
    0.08
     gourmet
    0.08
    otlin
    0.07
    歡
    0.07
    SAN
    0.07
     chocol
    0.06
    .folder
    0.06
    hma
    0.06
     ['$
    0.06
    Act Density 0.001%

    No Known Activations